Neural Computing and Applications

, Volume 28, Issue 5, pp 953–967 | Cite as

Evaluation of sampling method effects in 3D non-rigid registration

  • Marcelo Saval-Calvo
  • Jorge Azorin-Lopez
  • Andres Fuster-Guillo
  • Jose Garcia-Rodriguez
  • Sergio Orts-Escolano
  • Alberto Garcia-Garcia
Computational Intelligence for Vision and Robotics


Since the beginning of 3D computer vision problems, the use of techniques to reduce the data to make it treatable preserving the important aspects of the scene has been necessary. Currently, with the new low-cost RGB-D sensors, which provide a stream of color and 3D data of approximately 30 frames per second, this is getting more relevance. Many applications make use of these sensors and need a preprocessing to downsample the data in order to either reduce the processing time or improve the data (e.g., reducing noise or enhancing the important features). In this paper, we present a comparison of different downsampling techniques which are based on different principles. Concretely, five different downsampling methods are included: a bilinear-based method, a normal-based, a color-based, a combination of the normal and color-based samplings, and a growing neural gas (GNG)-based approach. For the comparison, two different models have been used acquired with the Blensor software. Moreover, to evaluate the effect of the downsampling in a real application, a 3D non-rigid registration is performed with the data sampled. From the experimentation we can conclude that depending on the purpose of the application some kernels of the sampling methods can improve drastically the results. Bilinear- and GNG-based methods provide homogeneous point clouds, but color-based and normal-based provide datasets with higher density of points in areas with specific features. In the non-rigid application, if a color-based sampled point cloud is used, it is possible to properly register two datasets for cases where intensity data are relevant in the model and outperform the results if only a homogeneous sampling is used.


3D downsampling Non-rigid registration Color registration 



This study was supported in part by the University of Alicante and Spanish government under Grants GRE11-01 and DPI2013-40534-R.


  1. 1.
    Castelló P, Chover M, Sbert M, Feixas M (2014) Reducing complexity in polygonal meshes with view-based saliency. Comput Aided Geom Des 31:279–293. doi: 10.1016/j.cagd.2014.05.001 MathSciNetCrossRefGoogle Scholar
  2. 2.
    Cignoni P, Montani C, Scopigno R (1997) A comparison of mesh simplification algorithms. Comput Graph 22:37–54CrossRefGoogle Scholar
  3. 3.
    Fritzke B (1995) A growing neural gas network learns topologies, vol 7. MIT Press, Cambridge, MA, pp 625–632Google Scholar
  4. 4.
    Gangwal OP, Berretty RP (2009) Depth map post-processing for 3D-TV. In: Digest of technical papers—IEEE international conference on consumer electronics. doi: 10.1109/ICCE.2009.5012253
  5. 5.
    Han H, Han X, Sun F, Huang C (2015) Point cloud simplification with preserved edge based on normal vector. Opt Int J Light Electron Opt. doi: 10.1016/j.ijleo.2015.05.092.
  6. 6.
    Henry P, Krainin M, Herbst E, Ren X, Fox D (2012) RGB-D mapping: using Kinect-style depth cameras for dense 3D modeling of indoor environments. doi: 10.1177/0278364911434148
  7. 7.
    Katz S, Tal A (2013) Improving the visual comprehension of point sets. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp 121–128. doi: 10.1109/CVPR.2013.23
  8. 8.
    Langmann B, Hartmann K, Loffeld O (2011) Comparison of depth super-resolution methods for 2D/3D images. Int J Comput Inf Syst Ind Manag Appl 3:635–645Google Scholar
  9. 9.
    Lee KH, Woo H, Suk T (2001) Point data reduction using 3D grids. doi: 10.1007/s001700170075
  10. 10.
    Li Y, Sun L (2010) A novel upsampling scheme for depth map compression in 3DTV system. In: 28th Picture coding symposium, PCS 2010, pp 186–189. doi: 10.1109/PCS.2010.5702456
  11. 11.
    Mamou K, Ghorbel F (2009) A simple and efficient approach for 3D mesh approximate convex decomposition. In: Image processing (ICIP), 2009 16th IEEE international conference on. doi: 10.1109/ICIP.2009.5414068
  12. 12.
    McNeely WA, McNeely WA, Puterbaugh KD, Puterbaugh KD, Troy JJ, Troy JJ (1999) Six degree-of-freedom haptic rendering using voxel sampling. In: Computer Graphics (SIGGRAPH Proceedings), pp 401–408. doi: 10.1145/1198555.1198605
  13. 13.
    Mora-Mora H, Mora-Pascual J, García-Chamizo JM, Jimeno-Morenilla A (2006) Real-time arithmetic unit. Real-Time Syst 34(1):53–79CrossRefzbMATHGoogle Scholar
  14. 14.
    Myronenko A, Song X (2010) Point set registration: coherent point drift. IEEE Trans Pattern Anal Mach Intell 32(12):2262–2275. doi: 10.1109/TPAMI.2010.46 CrossRefGoogle Scholar
  15. 15.
    Nehab D, Shilane P (2004) Stratified point sampling of 3D models. In: Proceedings of the first eurographics conference on point-based graphics, SPBG’04. Eurographics Association, Aire-la-Ville, Switzerland, pp 49–56. doi: 10.2312/SPBG/SPBG04/049-056
  16. 16.
    Newcombe RA, Davison AJ, Izadi S, Kohli P, Hilliges O, Shotton J, Molyneaux D, Hodges S, Kim D, Fitzgibbon A (2011) KinectFusion: real-time dense surface mapping and tracking. In: 2011 10th IEEE international symposium on mixed and augmented reality. IEEE, pp 127–136. doi: 10.1109/ISMAR.2011.6092378
  17. 17.
    Orts-Escolano S, Garcia-Rodriguez J, Morell V, Cazorla M, Garcia-Chamizo J (2014) 3d colour object reconstruction based on growing neural gas. In: Neural networks (IJCNN), 2014 international joint conference on, pp 1474–1481Google Scholar
  18. 18.
    Orts-Escolano S, Morell V, Garcia-Rodriguez J, Cazorla M (2013) Point cloud data filtering and downsampling using growing neural gas. In: The 2013 international joint conference on neural networks, IJCNN 2013. Dallas, TX, USA, pp 1–8Google Scholar
  19. 19.
    Ryde J, Hu H (2010) 3D mapping with multi-resolution occupied voxel lists. Auton Robots 28:169–185. doi: 10.1007/s10514-009-9158-3 CrossRefGoogle Scholar
  20. 20.
    Scharstein D, Szeliski R (2003) High-accuracy stereo depth maps using structured light. In: 2003 IEEE computer society conference on computer vision and pattern recognition, vol 1, Proceedings. doi: 10.1109/CVPR.2003.1211354
  21. 21.
    Schnabel R, Klein R (2006) Octree-based point-cloud compression. In: SPBG, pp 111–120. doi: 10.2312/SPBG/SPBG06/111-120
  22. 22.
    Schwarz H, Marpe D, Wiegand T (2007) Overview of the scalable video coding extension of the H.264/AVC standard. IEEE Trans Circuits Syst Video Technol 17:1103–1120. doi: 10.1109/TCSVT.2007.905532 CrossRefGoogle Scholar
  23. 23.
    Shi BQ, Liang J, Liu Q (2011) Adaptive simplification of point cloud using k-means clustering. Comput Aided Des 43:910–922. doi: 10.1016/j.cad.2011.04.001 CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2016

Authors and Affiliations

  • Marcelo Saval-Calvo
    • 1
  • Jorge Azorin-Lopez
    • 1
  • Andres Fuster-Guillo
    • 1
  • Jose Garcia-Rodriguez
    • 1
  • Sergio Orts-Escolano
    • 1
  • Alberto Garcia-Garcia
    • 1
  1. 1.University of AlicanteSan Vicente del RaspeigSpain

Personalised recommendations